Triple
T6951563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cours Saleya flower market |
E160936
|
entity |
| Predicate | hasSpecialSchedule |
P34861
|
FINISHED |
| Object | antiques and flea market on Mondays |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: antiques and flea market on Mondays | Statement: [Cours Saleya flower market, hasSpecialSchedule, antiques and flea market on Mondays]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpecialSchedule Context triple: [Cours Saleya flower market, hasSpecialSchedule, antiques and flea market on Mondays]
-
A.
hasWorkSchedule
Indicates that an entity is assigned or follows a specific work schedule, defining when they are expected to work.
-
B.
includesSpecialDay
chosen
Indicates that a time period, schedule, or collection contains or encompasses at least one designated special day or occasion.
-
C.
hasAdministrationSchedule
Indicates that there is a defined plan or timetable specifying when and how an entity is to be administered or given.
-
D.
hasScheduleType
Indicates that an entity is associated with a particular kind or category of schedule (e.g., recurring, one-time, or specific scheduling pattern).
-
E.
hasSpecialRules
Indicates that certain entities are governed by additional or exceptional rules that differ from the standard ones.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c68850419081909fb426b8f5a304c7 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dacca12481908942ba793a104cc3 |
completed | March 27, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69c6d7bf0a7c8190b5ed4aca22ba9b97 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:29 p.m.